OpenAI will embed Apollo researchers to investigate AI subversion
Article image or reusable cover for TechCrunch AI
OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.
The text is the source's own description of its publication. The content belongs to TechCrunch AI.
More from TechCrunch AI
Signal restricts mobile screenshots as it confronts ‘existential threat’ of AI surveillance
TechCrunch AI 15 h ago
A tale of two Nvidias
TechCrunch AI 15 h ago
Is selling an AI version of your face to this microdrama startup the future of Hollywood?
TechCrunch AI 21 h ago
Experts say AI has made planning cyberattacks on industrial equipment faster by helping attackers read manuals and research past accidents more quickly
Techmeme 2 h ago
